AI Paper Atlas

Research map / Point clouds / Segmentation and detection

Active Perception using Light Curtains for Autonomous Driving

Siddharth Ancha, Yaadhav Raaj, Peiyun Hu, Srinivasa G. Narasimhan, David Held

ECCV 2020 · Point clouds › Segmentation and detection · approach: LiDAR voxel and pillar detectors · 9 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add first light curtain placed on uncertain regionsdetector with single-beam LiDAR · Virtual KITTI3D mAP @0.5 IoU: 39.91 -> 58.01Improved
add first light curtain placed on uncertain regionsdetector with single-beam LiDAR · SYNTHIA3D mAP @0.5 IoU: 60.49 -> 68.79Improved
add second and third light curtainsdetector · Virtual KITTI3D mAP @0.5 IoU: 58.01 -> 60.86 -> 68.52Improved
add second and third light curtainsdetector · SYNTHIA3D mAP @0.7 IoU: 55.99 -> 57.08 -> 57.30Improved
train jointly with light curtain data instead of single-beam only, evaluated on single beam (ablation)detector · Virtual KITTI3D mAP @0.5 IoU: 42.35 -> 39.91Hurt
place curtains by dynamic programming instead of random depthlight curtain placement · Virtual KITTI3D mAP @0.5 IoU: 41.29 -> 58.01Improved
place curtains by dynamic programming instead of greedy optimization (ablation)light curtain placement · Virtual KITTI3D mAP @0.5 IoU: 37.40 -> 58.01Improved
allow flexible curtain shapes instead of frontoparallel at max uncertainty depth (ablation)light curtain placement · SYNTHIA3D mAP @0.5 IoU: 60.36 -> 68.79Improved
use uncertainty map instead of fixed depth 15m (ablation)light curtain placement · Virtual KITTI3D mAP @0.5 IoU: 44.99 -> 58.01Improved
add online light curtain data generation during training (ablation)detector training · Virtual KITTI3D mAP @0.5 IoU with 3 curtains: 0.68 -> 68.52Improved
add 10% noise to light curtain inputdetector · Virtual KITTI3D mAP @0.7 IoU with 1 curtain: 35.29 -> 25.99Hurt
add 10% noise to light curtain inputdetector · Virtual KITTI3D mAP @0.5 IoU with 3 curtains: 68.52 -> 60.02No clear effect

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy